Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion

TL;DR

Spatial-Mamba introduces a structure-aware state fusion mechanism in visual state space models, effectively capturing complex spatial dependencies in images with improved efficiency, leading to state-of-the-art results in vision tasks.

Contribution

It proposes a novel structure-aware state fusion approach that directly models spatial dependencies in visual state space models, unifying existing methods and enhancing performance.

Findings

Achieves state-of-the-art results in image classification, detection, and segmentation.

Unifies Mamba and linear attention under a matrix multiplication framework.

Operates effectively with a single scan, reducing computational costs.

Abstract

Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D sequences and employ various scanning patterns to incorporate local spatial dependencies. However, these methods are limited in effectively capturing the complex image spatial structures and the increased computational cost caused by the lengthened scanning paths. To address these limitations, we propose Spatial-Mamba, a novel approach that establishes neighborhood connectivity directly in the state space. Instead of relying solely on sequential state transitions, we introduce a structure-aware state fusion equation, which leverages dilated convolutions to capture image spatial structural dependencies, significantly enhancing the flow of visual contextual information. Spatial-Mamba proceeds in three stages: initial state computation in a unidirectional scan, spatial context acquisition through structure-aware state fusion, and final state computation using the observation equation. Our theoretical analysis shows that Spatial-Mamba unifies the original Mamba and linear attention under the same matrix multiplication framework, providing a deeper understanding of our method. Experimental results demonstrate that Spatial-Mamba, even with a single scan, attains or surpasses the state-of-the-art SSM-based models in image classification, detection and segmentation. Source codes and trained models can be found at https://github.com/EdwardChasel/Spatial-Mamba.